The aim of the present study is to investigate and explore the capability of the multilayer perceptron neural network to classify seismic signals recorded by the local seismic network of Agadir (M orocco). The problem is divided into two main steps, the feature extraction step and classification step. In the former, relevant discriminant features are extracted from the seismic signal based on the time and frequency domains. These are selected based on the analysts' experience. In the latter step, a process of trial an error was carried out to find the best neural network architecture. Classification results on a data set of 343 seis mic signals have demonstrated that the accuracy of the proposed classier can achieve more than 94%.

In this paper, a mathematical model dealing with a coupled heat, air, and moisture transfer in a building envelope was developed. Based on the three‐following driving potential: vapor pressure, dry air pressure, and temperature, an application on a hygrothermal behavior of a real wall was carried out for different climatic conditions. For this purpose, a characterization of the heat and moisture properties of the materials constituting the wall made with red brick and cement mortar was carried out in the laboratory. This was used to evaluate experimentally the input parameters of the model as a function of relative humidity. To validate the numerical model, an experimental platform was improved. The wall was set up in a double‐climatic chamber with different boundary conditions, and then the temperature and humidity evolutions were recorded using several sensors within the wall thickness. The results have highlighted a good agreement between numerical simulation results and experimental ones.

No abstract

No abstract

No abstract